初始化医疗报告生成项目，添加核心代码文件

2026-02-13 18:32:52 +08:00
commit faaf2158d4
69 changed files with 29836 additions and 0 deletions
--- a/backend/services/deepseek_health_service.py
+++ b/backend/services/deepseek_health_service.py
@@ -0,0 +1,480 @@
+"""
+DeepSeek 健康评估与建议生成服务
+用于生成"整体健康状况"和"功能性健康建议"内容
+
+优化：优先使用模板中已有的项目解释，只有模板中没有的项目才调用 DeepSeek 生成
+"""
+
+import os
+import json
+import requests
+from pathlib import Path
+from typing import List, Dict, Any
+
+
+class DeepSeekHealthService:
+    """DeepSeek 健康内容生成服务"""
+    
+    def __init__(self, api_key: str = None):
+        self.api_key = api_key or os.getenv("DEEPSEEK_API_KEY", "")
+        self.api_url = "https://api.deepseek.com/v1/chat/completions"
+        
+        # 加载模板中的解释
+        self.template_explanations = self._load_template_explanations()
+    
+    def _load_template_explanations(self) -> Dict[str, Dict[str, str]]:
+        """加载模板中已有的项目解释"""
+        explanations_file = Path(__file__).parent.parent / "template_explanations.json"
+        
+        if explanations_file.exists():
+            try:
+                with open(explanations_file, 'r', encoding='utf-8') as f:
+                    explanations = json.load(f)
+                print(f"  ✓ 已加载 {len(explanations)} 个模板解释")
+                return explanations
+            except Exception as e:
+                print(f"  ⚠️ 加载模板解释失败: {e}")
+        
+        return {}
+    
+    def get_template_explanation(self, abb: str) -> Dict[str, str]:
+        """
+        获取模板中的项目解释
+        
+        Args:
+            abb: 项目缩写
+            
+        Returns:
+            {"clinical_en": "...", "clinical_cn": "..."} 或空字典
+        """
+        # 尝试多种匹配方式
+        abb_upper = abb.upper().strip()
+        
+        # 直接匹配
+        if abb_upper in self.template_explanations:
+            return self.template_explanations[abb_upper]
+        
+        # 去除特殊字符后匹配
+        abb_clean = ''.join(c for c in abb_upper if c.isalnum())
+        for key, value in self.template_explanations.items():
+            key_clean = ''.join(c for c in key if c.isalnum())
+            if abb_clean == key_clean:
+                return value
+        
+        return {}
+    
+    def is_available(self) -> bool:
+        """检查服务是否可用"""
+        return bool(self.api_key)
+    
+    def call_deepseek(self, prompt: str) -> str:
+        """调用 DeepSeek API"""
+        if not self.api_key:
+            raise ValueError("未配置 DEEPSEEK_API_KEY")
+        
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json"
+        }
+        
+        data = {
+            "model": "deepseek-chat",
+            "messages": [{"role": "user", "content": prompt}],
+            "temperature": 0.1,
+            "max_tokens": 8000
+        }
+        
+        response = requests.post(
+            self.api_url, 
+            headers=headers, 
+            json=data, 
+            timeout=120
+        )
+        response.raise_for_status()
+        return response.json()["choices"][0]["message"]["content"]
+    
+    def collect_abnormal_items(self, analysis: Dict[str, Any]) -> List[Dict[str, str]]:
+        """
+        从分析结果中收集异常项
+        
+        Args:
+            analysis: LLM 分析结果，包含 abnormal_items 字段
+            
+        Returns:
+            异常项列表
+        """
+        abnormal_items = []
+        
+        # 从 abnormal_items 字段提取
+        raw_items = analysis.get("abnormal_items", [])
+        
+        for item in raw_items:
+            if isinstance(item, dict):
+                abnormal_items.append({
+                    "name": item.get("name", ""),
+                    "abb": item.get("abb", item.get("name", "")),
+                    "result": str(item.get("result", item.get("value", ""))),
+                    "reference": item.get("reference", ""),
+                    "unit": item.get("unit", ""),
+                    "level": item.get("level", ""),
+                    "point": "↑" if item.get("level") == "high" else ("↓" if item.get("level") == "low" else "")
+                })
+            elif isinstance(item, str):
+                # 如果是字符串格式，尝试解析
+                abnormal_items.append({
+                    "name": item,
+                    "abb": "",
+                    "result": "",
+                    "reference": "",
+                    "unit": "",
+                    "level": "",
+                    "point": ""
+                })
+        
+        return abnormal_items
+    
+    def get_item_explanations(self, abnormal_items: List[Dict[str, str]]) -> Dict[str, Dict[str, str]]:
+        """
+        为异常项获取解释（优先使用模板中的解释，缺失的才调用 DeepSeek 生成）
+        
+        Args:
+            abnormal_items: 异常项列表
+            
+        Returns:
+            {
+                "ABB": {"clinical_en": "...", "clinical_cn": "..."},
+                ...
+            }
+        """
+        explanations = {}
+        items_need_generation = []
+        
+        print("\n  📋 检查模板中的项目解释...")
+        
+        for item in abnormal_items:
+            abb = item.get("abb", "").upper().strip()
+            name = item.get("name", "")
+            
+            if not abb:
+                continue
+            
+            # 尝试从模板获取解释
+            template_exp = self.get_template_explanation(abb)
+            
+            if template_exp and template_exp.get("clinical_en") and template_exp.get("clinical_cn"):
+                explanations[abb] = template_exp
+                print(f"    ✓ {abb}: 使用模板解释")
+            else:
+                items_need_generation.append(item)
+                print(f"    ○ {abb}: 需要生成解释")
+        
+        # 如果有需要生成的项目，调用 DeepSeek
+        if items_need_generation and self.api_key:
+            print(f"\n  🤖 调用 DeepSeek 为 {len(items_need_generation)} 个项目生成解释...")
+            generated = self._generate_missing_explanations(items_need_generation)
+            explanations.update(generated)
+        
+        return explanations
+    
+    def _generate_missing_explanations(self, items: List[Dict[str, str]]) -> Dict[str, Dict[str, str]]:
+        """
+        调用 DeepSeek 为缺失解释的项目生成临床意义
+        
+        Args:
+            items: 需要生成解释的项目列表
+            
+        Returns:
+            生成的解释字典
+        """
+        if not items:
+            return {}
+        
+        # 构建项目描述
+        items_desc = []
+        for item in items:
+            desc = f"- {item['abb']}: {item['name']}"
+            if item.get('result'):
+                desc += f", 结果: {item['result']}"
+            if item.get('unit'):
+                desc += f" {item['unit']}"
+            if item.get('reference'):
+                desc += f", 参考范围: {item['reference']}"
+            items_desc.append(desc)
+        
+        prompt = f"""你是一位医学检验专家，请为以下医疗检测项目生成临床意义解释。
+
+## 需要解释的项目：
+{chr(10).join(items_desc)}
+
+## 要求：
+1. 为每个项目提供英文和中文的临床意义解释
+2. 解释应包含：该指标的作用、正常范围的意义、异常时可能的原因
+3. 语言专业但易于理解
+4. 每个解释约50-100字
+
+## 输出格式（JSON）：
+```json
+{{
+    "ABB1": {{
+        "clinical_en": "English clinical significance...",
+        "clinical_cn": "中文临床意义..."
+    }},
+    "ABB2": {{
+        "clinical_en": "...",
+        "clinical_cn": "..."
+    }}
+}}
+```
+
+只返回JSON，不要其他说明。"""
+        
+        try:
+            response = self.call_deepseek(prompt)
+            
+            # 解析 JSON
+            if "```json" in response:
+                response = response.split("```json")[1].split("```")[0]
+            elif "```" in response:
+                response = response.split("```")[1].split("```")[0]
+            
+            result = json.loads(response.strip())
+            print(f"    ✓ 成功生成 {len(result)} 个项目的解释")
+            return result
+        except Exception as e:
+            print(f"    ✗ 生成解释失败: {e}")
+            return {}
+    
+    def generate_health_assessment(self, abnormal_items: List[Dict[str, str]]) -> Dict[str, Any]:
+        """
+        生成"整体健康状况"评估内容
+        
+        Args:
+            abnormal_items: 异常项列表
+            
+        Returns:
+            包含多个小节的健康评估内容
+        """
+        if not self.api_key or not abnormal_items:
+            return {"sections": []}
+        
+        # 构建异常项描述
+        abnormal_desc = []
+        for item in abnormal_items:
+            direction = "偏高" if item.get("point") in ["↑", "H", "高"] or item.get("level") == "high" else "偏低"
+            desc = f"- {item['name']}"
+            if item.get('abb'):
+                desc += f" ({item['abb']})"
+            desc += f": {item['result']}"
+            if item.get('unit'):
+                desc += f" {item['unit']}"
+            desc += f" ({direction}"
+            if item.get('reference'):
+                desc += f", 参考范围: {item['reference']}"
+            desc += ")"
+            abnormal_desc.append(desc)
+        
+        prompt = f"""你是一位功能医学专家，请根据以下所有异常检测指标，撰写"整体健康状况评估"的内容。
+
+## 异常指标：
+{chr(10).join(abnormal_desc)}
+
+## 要求：
+1. 根据异常指标的类型，自动分成合适的小节（如血液学、内分泌、免疫、代谢等，根据实际异常项决定）
+2. 每个小节包含英文和中文两个版本
+3. 从功能医学和整体健康角度分析
+4. 解释可能的原因和健康影响
+5. 语言专业但易于理解
+6. 每个小节的每个语言版本约150-250字
+
+## 输出格式（JSON）：
+```json
+{{
+    "sections": [
+        {{
+            "title_en": "(I) Section Title in English",
+            "title_cn": "（一）中文小节标题",
+            "content_en": "English analysis content...",
+            "content_cn": "中文分析内容..."
+        }}
+    ]
+}}
+```
+
+只返回JSON，不要其他说明。根据实际异常项情况决定分几个小节，不要硬套固定模板。"""
+        
+        try:
+            response = self.call_deepseek(prompt)
+            
+            # 解析 JSON
+            if "```json" in response:
+                response = response.split("```json")[1].split("```")[0]
+            elif "```" in response:
+                response = response.split("```")[1].split("```")[0]
+            
+            result = json.loads(response.strip())
+            print(f"    ✓ 生成健康评估内容，共 {len(result.get('sections', []))} 个小节")
+            return result
+        except Exception as e:
+            print(f"    ✗ 生成健康评估内容失败: {e}")
+            return {"sections": []}
+    
+    def generate_health_advice(self, abnormal_items: List[Dict[str, str]]) -> Dict[str, Any]:
+        """
+        生成"功能性健康建议"内容
+        
+        Args:
+            abnormal_items: 异常项列表
+            
+        Returns:
+            包含5个固定小节的健康建议内容
+        """
+        if not self.api_key or not abnormal_items:
+            return {"sections": []}
+        
+        # 异常项描述
+        abnormal_desc = []
+        for item in abnormal_items:
+            direction = "偏高" if item.get("point") in ["↑", "H", "高"] or item.get("level") == "high" else "偏低"
+            desc = f"- {item['name']}"
+            if item.get('abb'):
+                desc += f" ({item['abb']})"
+            desc += f": {item['result']}"
+            if item.get('unit'):
+                desc += f" {item['unit']}"
+            desc += f" ({direction})"
+            abnormal_desc.append(desc)
+        
+        prompt = f"""你是一位功能医学专家，请根据以下异常检测指标，撰写"功能医学健康建议"的内容。
+
+## 异常指标：
+{chr(10).join(abnormal_desc)}
+
+## 要求：
+1. 必须包含以下5个固定小节（按顺序）：
+   - Nutrition Intervention 营养干预
+   - Exercise Intervention 运动干预  
+   - Sleep & Stress Management 睡眠与压力管理
+   - Lifestyle Adjustment 生活方式调整
+   - Long-term Follow-up Plan 长期随访计划
+2. 每个小节针对这些异常指标提供具体、可执行的建议
+3. 从功能医学角度出发，强调预防和整体调理
+4. 每个小节包含3-5条具体建议措施
+5. 语言专业但易于理解
+6. 分别提供英文和中文版本
+7. 每个小节的每个语言版本约200-300字
+
+## 输出格式（JSON）：
+```json
+{{
+    "sections": [
+        {{
+            "title_en": "Nutrition Intervention",
+            "title_cn": "营养干预",
+            "content_en": "English nutrition advice...",
+            "content_cn": "中文营养建议..."
+        }},
+        {{
+            "title_en": "Exercise Intervention",
+            "title_cn": "运动干预",
+            "content_en": "...",
+            "content_cn": "..."
+        }},
+        {{
+            "title_en": "Sleep & Stress Management",
+            "title_cn": "睡眠与压力管理",
+            "content_en": "...",
+            "content_cn": "..."
+        }},
+        {{
+            "title_en": "Lifestyle Adjustment",
+            "title_cn": "生活方式调整",
+            "content_en": "...",
+            "content_cn": "..."
+        }},
+        {{
+            "title_en": "Long-term Follow-up Plan",
+            "title_cn": "长期随访计划",
+            "content_en": "...",
+            "content_cn": "..."
+        }}
+    ]
+}}
+```
+
+只返回JSON，不要其他说明。"""
+        
+        try:
+            response = self.call_deepseek(prompt)
+            
+            # 解析 JSON
+            if "```json" in response:
+                response = response.split("```json")[1].split("```")[0]
+            elif "```" in response:
+                response = response.split("```")[1].split("```")[0]
+            
+            result = json.loads(response.strip())
+            print(f"    ✓ 生成健康建议内容，共 {len(result.get('sections', []))} 个小节")
+            return result
+        except Exception as e:
+            print(f"    ✗ 生成健康建议内容失败: {e}")
+            return {"sections": []}
+    
+    def generate_health_content(self, analysis: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        生成完整的健康评估和建议内容
+        
+        优化：优先使用模板中已有的项目解释，只有模板中没有的项目才调用 DeepSeek 生成
+        
+        Args:
+            analysis: LLM 分析结果
+            
+        Returns:
+            包含 health_assessment, health_advice, item_explanations 的字典
+        """
+        if not self.is_available():
+            print("  ⚠️ DeepSeek API Key 未配置，跳过健康内容生成")
+            return {}
+        
+        print("\n============================================================")
+        print("DeepSeek 健康内容生成")
+        print("============================================================")
+        
+        # 收集异常项
+        print("\n  📝 正在收集异常项...")
+        abnormal_items = self.collect_abnormal_items(analysis)
+        
+        if not abnormal_items:
+            print("    ℹ️ 没有检测到异常项目，跳过内容生成")
+            return {}
+        
+        print(f"    发现 {len(abnormal_items)} 个异常项目:")
+        for item in abnormal_items[:10]:
+            direction = "↑" if item.get("level") == "high" or item.get("point") == "↑" else "↓"
+            print(f"      - {item['name']}: {item['result']} {direction}")
+        if len(abnormal_items) > 10:
+            print(f"      ... 等共 {len(abnormal_items)} 项")
+        
+        # 获取项目解释（优先使用模板，缺失的才生成）
+        item_explanations = self.get_item_explanations(abnormal_items)
+        
+        # 统计使用情况
+        template_count = sum(1 for abb in item_explanations if self.get_template_explanation(abb))
+        generated_count = len(item_explanations) - template_count
+        print(f"\n  📊 解释来源统计: 模板 {template_count} 个, DeepSeek生成 {generated_count} 个")
+        
+        # 生成健康评估
+        print("\n  🤖 正在调用 DeepSeek 生成整体健康状况...")
+        health_assessment = self.generate_health_assessment(abnormal_items)
+        
+        # 生成健康建议
+        print("\n  🤖 正在调用 DeepSeek 生成功能性健康建议...")
+        health_advice = self.generate_health_advice(abnormal_items)
+        
+        print("\n  ✓ 健康内容生成完成")
+        
+        return {
+            "health_assessment": health_assessment,
+            "health_advice": health_advice,
+            "abnormal_items": abnormal_items,
+            "item_explanations": item_explanations  # 包含每个项目的解释
+        }